发现最适合你需求的 AI 技能
Backup the agent workspace to a GitHub repository. Use when: asked to save/remember something important, after significant changes to memory files, on a schedule, or when asked to push workspace to git. Handles token discovery, repo initialization, and push. If no GitHub token is available, asks the owner for a PAT before proceeding.
Post content to GitHub Gist and get back a shareable URL. Rich context sharing between agents, operators, and humans.
Post content to GitHub Gist and get back a shareable URL. Rich context sharing between agents, operators, and humans.
Use this skill when operating Ghosthand, a local Android control runtime exposed over a loopback HTTP API for OpenClaw or another agent. Trigger it for Ghosthand tasks involving runtime or capability checks, structured UI inspection, selector planning, semantic clicks, coordinate taps, text input, scrolling, wait conditions, clipboard transfer, notifications, screenshots, or debugging Ghosthand-specific route behavior such as partial-output warnings, snapshot-scoped node IDs, or text vs content
|
Dual-core efficiency improvement skill: (1) Actively collect user work background, preference habits through Socratic guided Q&A, automatically sync and update configuration files, zero-threshold to build fully personalized OpenClaw; (2) Standardize negative feedback/skill optimization processing workflow, after receiving requirements, first communicate specific issues clearly, output optimization plan, execute only after user 100% confirms satisfaction, fundamentally eliminate invalid back-and-
AI-powered personal secretary for task management and goal tracking. Gives you a Top 3 daily brief, captures ideas, tracks momentum, adapts to your available time and energy. Works with any model. Local-first, no data leaves your machine.
Free version — audit your content for AI search citability with the GEO Scorecard. Covers 4 of 8 dimensions.
Analyze 23andMe raw genome data to generate comprehensive health, trait, and family comparison reports. Supports cardiovascular, cognitive, metabolic, pharmacogenomic, athletic, and ancestry analysis. Use when user asks to analyze genome data, 23andMe files, genetic reports, SNP analysis, health risk from DNA, or family genetic comparison.
通过交互式需求分析生成完整的 PRD 文档。基于领域知识库进行结构化提问和数据流推导，确保需求理解和数据流的完整性。仅当用户要「生成 PRD/需求文档」时使用；分析现有代码库请用 analyze。
通过交互式技术选型生成系统设计文档。基于领域知识库进行数据模型设计和集成设计，确保设计与 PRD 数据流对齐。仅当用户要「生成系统设计文档」时使用；分析现有代码库请用 analyze，从代码反推设计主线请用 analyze --phase=deep。
基于模板为当前工作空间生成完整技术编码规范，写入 docs/coding-specs/，供 gen-code 与其它技能消费。
